Phoneme-BERT: Joint Language Modelling of Phoneme Sequence and ASR Transcript
This addresses ASR error robustness for noisy and out-of-domain data in NLP tasks, representing a novel method for a known bottleneck.
The authors tackled the problem of ASR errors degrading downstream NLP task performance by proposing PhonemeBERT, a joint language model of phoneme sequences and ASR transcripts, which comprehensively beat state-of-the-art baselines on sentiment, question, and intent classification datasets.
Recent years have witnessed significant improvement in ASR systems to recognize spoken utterances. However, it is still a challenging task for noisy and out-of-domain data, where substitution and deletion errors are prevalent in the transcribed text. These errors significantly degrade the performance of downstream tasks. In this work, we propose a BERT-style language model, referred to as PhonemeBERT, that learns a joint language model with phoneme sequence and ASR transcript to learn phonetic-aware representations that are robust to ASR errors. We show that PhonemeBERT can be used on downstream tasks using phoneme sequences as additional features, and also in low-resource setup where we only have ASR-transcripts for the downstream tasks with no phoneme information available. We evaluate our approach extensively by generating noisy data for three benchmark datasets - Stanford Sentiment Treebank, TREC and ATIS for sentiment, question and intent classification tasks respectively. The results of the proposed approach beats the state-of-the-art baselines comprehensively on each dataset.